© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41944
    Prev
    Next
    INDEX
    Explanations

    writing numbers or dates

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    чә
    0.46
     сможете
    0.46
    üğünüz
    0.42
    臓
    0.41
    до
    0.40
    本科
    0.39
     LOGIN
    0.39
    腧
    0.39
     \
    0.38
    сте
    0.38
    POSITIVE LOGITS
     वरना
    0.47
     এড়িয়ে
    0.46
     गठित
    0.41
     vermeiden
    0.41
     définie
    0.41
     फीसदी
    0.40
     nummer
    0.39
     نیم
    0.39
     heightened
    0.39
     quizz
    0.39
    Activations Density 0.000%

    No Known Activations